{"id":"https://openalex.org/W2617069179","doi":"https://doi.org/10.24963/ijcai.2017/656","title":"Reinforcement Learning with a Corrupted Reward Channel","display_name":"Reinforcement Learning with a Corrupted Reward Channel","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2617069179","doi":"https://doi.org/10.24963/ijcai.2017/656","mag":"2617069179"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/656","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/656","pdf_url":"https://www.ijcai.org/proceedings/2017/0656.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0656.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020224050","display_name":"Tom Everitt","orcid":"https://orcid.org/0000-0003-1210-9866"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Tom Everitt","raw_affiliation_strings":["Australian National University"],"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052300917","display_name":"Victoria Krakovna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victoria Krakovna","raw_affiliation_strings":["DeepMind"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110938957","display_name":"Laurent Orseau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laurent Orseau","raw_affiliation_strings":["DeepMind"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008987732","display_name":"Shane Legg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shane Legg","raw_affiliation_strings":["DeepMind"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020224050"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":4.546,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95175542,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4705","last_page":"4713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9484999775886536,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9218000173568726,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8647264242172241},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6920846104621887},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6274495124816895},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5223261713981628},{"id":"https://openalex.org/keywords/language-change","display_name":"Language change","score":0.506402850151062},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4810081422328949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39730340242385864},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.22744452953338623},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19574975967407227},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12184986472129822},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10355985164642334},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07518160343170166}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8647264242172241},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6920846104621887},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6274495124816895},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5223261713981628},{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.506402850151062},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4810081422328949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39730340242385864},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.22744452953338623},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19574975967407227},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12184986472129822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10355985164642334},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07518160343170166},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2017/656","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/656","pdf_url":"https://www.ijcai.org/proceedings/2017/0656.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1705.08417","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.08417","pdf_url":"https://arxiv.org/pdf/1705.08417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2617069179","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1705.08417","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/313143","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/313143","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17)","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.1705.08417","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.08417","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/656","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/656","pdf_url":"https://www.ijcai.org/proceedings/2017/0656.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2617069179.pdf","grobid_xml":"https://content.openalex.org/works/W2617069179.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1624823515","https://openalex.org/W2058879737","https://openalex.org/W2093399934","https://openalex.org/W2151554678","https://openalex.org/W2165131254","https://openalex.org/W2168359464","https://openalex.org/W2205847592","https://openalex.org/W2410842990","https://openalex.org/W2565840370","https://openalex.org/W2617069179","https://openalex.org/W2617173417"],"related_works":["https://openalex.org/W2800191438","https://openalex.org/W2986020463","https://openalex.org/W88199814","https://openalex.org/W2890882194","https://openalex.org/W2787193614","https://openalex.org/W2915060045","https://openalex.org/W2605369401","https://openalex.org/W2563830277","https://openalex.org/W2189559150","https://openalex.org/W3101172017","https://openalex.org/W3163049241","https://openalex.org/W2912748933","https://openalex.org/W2550770153","https://openalex.org/W3198608914","https://openalex.org/W3173218700","https://openalex.org/W1999874108","https://openalex.org/W194754089","https://openalex.org/W2757609746","https://openalex.org/W2963386671","https://openalex.org/W3175760761"],"abstract_inverted_index":{"No":[0],"real-world":[1],"reward":[2,45,109,130],"function":[3],"is":[4,46],"perfect.":[5],"Sensory":[6],"errors":[7,115],"and":[8,75,105],"software":[9],"bugs":[10],"may":[11,29,116],"result":[12],"in":[13,68,101],"agents":[14],"getting":[15],"higher":[16],"(or":[17],"lower)":[18],"rewards":[19],"than":[20],"they":[21],"should.":[22],"For":[23],"example,":[24],"a":[25,33,54],"reinforcement":[26,103,107],"learning":[27,104],"agent":[28,96],"prefer":[30],"states":[31],"where":[32,42],"sensory":[34,114],"error":[35],"gives":[36],"it":[37],"the":[38,43,81,88,95,127],"maximum":[39],"reward,":[40],"but":[41],"true":[44],"actually":[47],"small.":[48],"We":[49],"formalise":[50],"this":[51],"problem":[52,89],"as":[53,100],"generalised":[55],"Markov":[56],"Decision":[57],"Problem":[58],"called":[59],"Corrupt":[60],"Reward":[61],"MDP.":[62],"Traditional":[63],"RL":[64],"methods":[65],"fare":[66],"poorly":[67],"CRMDPs,":[69],"even":[70],"under":[71,136],"strong":[72],"simplifying":[73],"assumptions":[74],"when":[76],"trying":[77],"to":[78,125],"compensate":[79],"for":[80],"possibly":[82],"corrupt":[83],"rewards.":[84],"Two":[85],"ways":[86],"around":[87],"are":[90],"investigated.":[91],"First,":[92],"by":[93,122],"giving":[94],"richer":[97],"data,":[98],"such":[99],"inverse":[102],"semi-supervised":[106],"learning,":[108],"corruption":[110,131],"stemming":[111],"from":[112],"systematic":[113],"sometimes":[117],"be":[118,133],"completely":[119],"managed.":[120],"Second,":[121],"using":[123],"randomisation":[124],"blunt":[126],"agent's":[128],"optimisation,":[129],"can":[132],"partially":[134],"managed":[135],"some":[137],"assumptions.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}